get_unobserved_model_predictions

a <code>data.frame</code> object with rows the models and
columns the drug combinations. Possible values for each model-drug combination
element are either 0 (no synergy predicted), 1 (synergy was
predicted) or NA (couldn't find stable states in either the drug
combination inhibited model or in any of the two single-drug inhibited models)

model.predictions

a character vector with elements the names of the
drug combinations that were found as synergistic

observed.synergies

Subset the model predictions to the (false) non-observed synergies

Analysis and visualization of an ensemble of boolean models for
biomarker discovery in cancer cell networks. The package allows to easily
import the data results of a software pipeline that predicts synergistic drug
combinations in cancer cell lines, developed by the DrugLogics research group
in NTNU. It has generic functions that can be used to split a boolean model
dataset to model groups with regards to the models predictive performance (number of true
positive predictions or Matthews correlation coefficient score) or synergy prediction based on a given set
of observed synergies and find the average activity difference per network
node between all group pairs. Thus, given user-specific thresholds,
important nodes (biomarkers) can be accessed in the sense that they make the
models predict specific synergies (synergy biomarkers) or have better
performance in general (performance biomarkers). Lastly, if the
boolean models have a specific equation form and differ only in their link operator,
link operator biomarkers can also be assessed.

get_unobserved_model_predictions: Subset the model predictions to the (false) non-observed synergies

Description

Usage

Arguments

Value